Zdrojový dokument:Data Science and Intelligent Systems : proceedings of 5th Computational Methods in Systems and Software 2021, Vol. 2
Název akce5th Computational Methods in Systems and Software, CoMeSySo 2021 (01.10.2021 - 01.10.2021, ONLINE)
Abstrakt:
Grasp point detection is a necessary ability to handle for industrial robots. In recent years, various deep learning-based techniques for robotic grasping have been introduced. To follow this trend, we introduce a convolutional neural network-based approach for model-free one step method for grasp point detection. This method provides all feasible grasp points suitable for parallel grippers, based on a single RGB image of the scene. A case study, which shows the outstanding accuracy of the presented approach as well as its acceptable response time, is presented at the end of this contribution.